Learning Theory

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data COLT 2022 Benign Underfitting of Stochastic Gradient Descent NeurIPS 2022 Best Arm Identification with Safety Constraints AISTATS 2022 Best Heuristic Identification for Constraint Satisfaction IJCAI 2022 Best of Both Worlds Model Selection NeurIPS 2022 Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules NeurIPS 2022 Beyond No Regret: Instance-Dependent PAC Reinforcement Learning COLT 2022 Beyond the Best: Distribution Functional Estimation in Infinite-Armed Bandits NeurIPS 2022 Bias-Variance Decompositions for Margin Losses AISTATS 2022 Black-Box Generalization: Stability of Zeroth-Order Learning NeurIPS 2022 Block Contextual MDPs for Continual Learning L4DC 2022 Bounding the Width of Neural Networks via Coupled Initialization A Worst Case Analysis ICML 2022 Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction IJCAI 2022 Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent From the Decision Boundary Perspective CVPR 2022 Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis AISTATS 2022 Can Q-learning be Improved with Advice? COLT 2022 Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views? ICLR 2022 Cascaded Gaps: Towards Logarithmic Regret for Risk-Sensitive Reinforcement Learning ICML 2022 Causal forecasting: generalization bounds for autoregressive models UAI 2022 Causal Transportability for Visual Recognition CVPR 2022 Chained generalisation bounds COLT 2022 Challenging Common Assumptions in Convex Reinforcement Learning NeurIPS 2022 Characterization of Excess Risk for Locally Strongly Convex Population Risk NeurIPS 2022 Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm AISTATS 2022 Characterizing Datapoints via Second-Split Forgetting NeurIPS 2022